FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136122620> ?p ?o ?g. }

• W3136122620 abstract "Perhaps surprisingly sewerage infrastructure is one of the most costly infrastructures in modern society. Sewer pipes are manually inspected to determine whether the pipes are defective. However, this process is limited by the number of qualified inspectors and the time it takes to inspect a pipe. Automatization of this process is therefore of high interest. So far, the success of computer vision approaches for sewer defect classification has been limited when compared to the success in other fields mainly due to the lack of public datasets. To this end, in this work we present a large novel and publicly available multi-label classification dataset for image-based sewer defect classification called Sewer-ML. The Sewer-ML dataset consists of 1.3 million images annotated by professional sewer inspectors from three different utility companies across nine years. Together with the dataset, we also present a benchmark algorithm and a novel metric for assessing performance. The benchmark algorithm is a result of evaluating 12 state-of-the-art algorithms, six from the sewer defect classification domain and six from the multi-label classification domain, and combining the best performing algorithms. The novel metric is a class-importance weighted F2 score, $text{F}2_{text{CIW}}$, reflecting the economic impact of each class, used together with the normal pipe F1 score, $text{F}1_{text{Normal}}$. The benchmark algorithm achieves an $text{F}2_{text{CIW}}$ score of 55.11% and $text{F}1_{text{Normal}}$ score of 90.94%, leaving ample room for improvement on the Sewer-ML dataset. The code, models, and dataset are available at the project page this https URL" @default.
• W3136122620 created "2021-03-29" @default.
• W3136122620 creator A5022176859 @default.
• W3136122620 creator A5040831022 @default.
• W3136122620 date "2021-03-19" @default.
• W3136122620 modified "2023-09-27" @default.
• W3136122620 title "Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark" @default.
• W3136122620 cites W1514027499 @default.
• W3136122620 cites W1566135517 @default.
• W3136122620 cites W1567302070 @default.
• W3136122620 cites W1861492603 @default.
• W3136122620 cites W1976499321 @default.
• W3136122620 cites W1994198993 @default.
• W3136122620 cites W2007972815 @default.
• W3136122620 cites W2031489346 @default.
• W3136122620 cites W2056132907 @default.
• W3136122620 cites W2097376151 @default.
• W3136122620 cites W2114315281 @default.
• W3136122620 cites W2163605009 @default.
• W3136122620 cites W2183341477 @default.
• W3136122620 cites W2194775991 @default.
• W3136122620 cites W2252376542 @default.
• W3136122620 cites W2279098554 @default.
• W3136122620 cites W2410641892 @default.
• W3136122620 cites W2422823951 @default.
• W3136122620 cites W2548476003 @default.
• W3136122620 cites W2560096627 @default.
• W3136122620 cites W2565639579 @default.
• W3136122620 cites W2605572715 @default.
• W3136122620 cites W2613718673 @default.
• W3136122620 cites W2622263826 @default.
• W3136122620 cites W2743059945 @default.
• W3136122620 cites W2792741217 @default.
• W3136122620 cites W2809273748 @default.
• W3136122620 cites W2886015888 @default.
• W3136122620 cites W2889035772 @default.
• W3136122620 cites W2897608264 @default.
• W3136122620 cites W2907258563 @default.
• W3136122620 cites W2912183379 @default.
• W3136122620 cites W2913697492 @default.
• W3136122620 cites W2918439310 @default.
• W3136122620 cites W2922005503 @default.
• W3136122620 cites W2932399282 @default.
• W3136122620 cites W2943574864 @default.
• W3136122620 cites W2950119225 @default.
• W3136122620 cites W2953888523 @default.
• W3136122620 cites W2957702778 @default.
• W3136122620 cites W2963052338 @default.
• W3136122620 cites W2963300078 @default.
• W3136122620 cites W2963306618 @default.
• W3136122620 cites W2963351448 @default.
• W3136122620 cites W2963466857 @default.
• W3136122620 cites W2963676620 @default.
• W3136122620 cites W2963691377 @default.
• W3136122620 cites W2963697527 @default.
• W3136122620 cites W2963745697 @default.
• W3136122620 cites W2963875806 @default.
• W3136122620 cites W2964015378 @default.
• W3136122620 cites W2966628364 @default.
• W3136122620 cites W2969792713 @default.
• W3136122620 cites W2970871020 @default.
• W3136122620 cites W2982112268 @default.
• W3136122620 cites W2982284503 @default.
• W3136122620 cites W2982512126 @default.
• W3136122620 cites W2997136715 @default.
• W3136122620 cites W2998420437 @default.
• W3136122620 cites W3000005686 @default.
• W3136122620 cites W3000521887 @default.
• W3136122620 cites W3008926194 @default.
• W3136122620 cites W3017475358 @default.
• W3136122620 cites W3034472074 @default.
• W3136122620 cites W3036205077 @default.
• W3136122620 cites W3082733954 @default.
• W3136122620 cites W3083543291 @default.
• W3136122620 cites W3090578762 @default.
• W3136122620 cites W3093478663 @default.
• W3136122620 cites W3095707208 @default.
• W3136122620 cites W3102424508 @default.
• W3136122620 cites W3110305765 @default.
• W3136122620 cites W3111544845 @default.
• W3136122620 cites W3121480429 @default.
• W3136122620 cites W3135550350 @default.
• W3136122620 hasPublicationYear "2021" @default.
• W3136122620 type Work @default.
• W3136122620 sameAs 3136122620 @default.
• W3136122620 citedByCount "0" @default.
• W3136122620 crossrefType "posted-content" @default.
• W3136122620 hasAuthorship W3136122620A5022176859 @default.
• W3136122620 hasAuthorship W3136122620A5040831022 @default.
• W3136122620 hasConcept C111919701 @default.
• W3136122620 hasConcept C119857082 @default.
• W3136122620 hasConcept C124101348 @default.
• W3136122620 hasConcept C127413603 @default.
• W3136122620 hasConcept C13280743 @default.
• W3136122620 hasConcept C134306372 @default.
• W3136122620 hasConcept C154945302 @default.
• W3136122620 hasConcept C165895018 @default.
• W3136122620 hasConcept C176217482 @default.
• W3136122620 hasConcept C185798385 @default.
• W3136122620 hasConcept C190714865 @default.

• next